Vol. 11:2 (2022) ► pp.184–212
Creativity in translation
Machine translation as a constraint for literary texts
This article presents the results of a study involving the translation of a short story by Kurt Vonnegut from English to Catalan and Dutch using three modalities: machine-translation (MT), post-editing (PE) and translation without aid (HT). Our aim is to explore creativity, understood to involve novelty and acceptability, from a quantitative perspective. The results show that HT has the highest creativity score, followed by PE, and lastly, MT, and this is unanimous from all reviewers. A neural MT system trained on literary data does not currently have the necessary capabilities for a creative translation; it renders literal solutions to translation problems. More importantly, using MT to post-edit raw output constrains the creativity of translators, resulting in a poorer translation often not fit for publication, according to experts.
Article outline
- Introduction
- Related Work
- Research methodology
- Source text
- Machine translation
- Translation process
- Translators
- Review process
- Measuring creativity
- Acceptability
- Units of creative potential (UCP)
- Novelty
- Creativity scoring
- Interviews
- Results
- Results on translators’ changes and effort
- HTER
- Translation effort according to PET
- Results from the review
- Post-task questionnaire
- Acceptability
- Creative Shifts
- Creativity Score
- Interviews with translators and reviewers
- 1.MT can only be partially useful in literary translation
- 2.Creativity is a problem-solving process
- 3.The proposals act as a constraint to creativity
- 4.The delicate equilibrium of reviewing
- 5.The ideal tool for literary translation is human centred
- 6.The technology or modality impact depends on the type of reader
- 7.The final translation as a product of many collaborative steps
- 8.The grim future of translation and technology
- Conclusions
- Acknowledgements
- Notes
-
References
https://doi.org/10.1075/ts.21025.gue